Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Hardware requirement for examples/rl/deep_q_network_breakout.py? #1850

Closed
haison8x opened this issue May 2, 2024 · 5 comments
Closed

Hardware requirement for examples/rl/deep_q_network_breakout.py? #1850

haison8x opened this issue May 2, 2024 · 5 comments

Comments

@haison8x
Copy link

haison8x commented May 2, 2024

May I ask the hardware requirements for examples/rl/deep_q_network_breakout.py?
I tried running this example in a server with 2GB RAM but it is corrupted after 2 hours, the virtual memory is 48 GB

@sachinprasadhs
Copy link
Collaborator

Hi,

Could you try to reduce the numbers of these parameters and check if you're able to get improvement.

batch_size = 32 
max_steps_per_episode = 10000
max_episodes = 10

@haison8x
Copy link
Author

haison8x commented May 2, 2024

Thanks
In case I want to run the full training session, which hardware specification should I use?

@haison8x haison8x closed this as completed May 2, 2024
@haison8x haison8x reopened this May 2, 2024
Copy link

github-actions bot commented May 2, 2024

Are you satisfied with the resolution of your issue?
Yes
No

@sachinprasadhs
Copy link
Collaborator

Thanks In case I want to run the full training session, which hardware specification should I use?

There is no benchmarking test or any other tests to guage the hardware requirement.

Usually, all the Keras tutorials are designed to work on the colab free runtime setup which is 12 GB ram.

You can try with 8-12 GB RAM setup and test it out.

Copy link

Are you satisfied with the resolution of your issue?
Yes
No

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants